{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robust-generalization-against-photon-limited","title":"Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization","arxiv_id":"2303.13087","date":"2023-03-23","proceeding":"CVPR 2023 1","authors":["Zhuo Huang","Miaoxi Zhu","Xiaobo Xia","Li Shen","Jun Yu","Chen Gong","Bo Han","Bo Du","Tongliang Liu"],"abstract":"Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.","url_abs":"https://arxiv.org/abs/2303.13087v1","url_pdf":"https://arxiv.org/pdf/2303.13087v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-generalization-against-photon-limited","repo_url":"https://github.com/zhuohuangai/sharpdro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-generalization-against-photon-limited","repo_url":"https://github.com/feedbackward/addro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-generalization-against-photon-limited","repo_url":"https://github.com/2024-MindSpore-1/Code10/tree/main/SharpDRO-ms-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"robust-generalization-against-photon-limited","repo_url":"https://github.com/yangyucheng000/papercode-2/tree/main/SharpDRO-ms-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.13087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13087"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code10/tree/main/SharpDRO-ms-main","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/feedbackward/addro","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhuohuangai/sharpdro","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/papercode-2/tree/main/SharpDRO-ms-main","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8c43c6c7c8a7a882","entry":"Loss_SoftAD","repo":"feedbackward/addro","repo_kind":"listed","path":"addro/setup/losses.py","file_url":"https://github.com/feedbackward/addro/blob/HEAD/addro/setup/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c43c6c7c8a7a882"}},{"code_sha256_prefix":"ef3414913760ce94","entry":"get_named_loss","repo":"feedbackward/addro","repo_kind":"listed","path":"addro/setup/losses.py","file_url":"https://github.com/feedbackward/addro/blob/HEAD/addro/setup/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef3414913760ce94"}},{"code_sha256_prefix":"5f9e3f7cfa214e9f","entry":"rho_torch","repo":"feedbackward/addro","repo_kind":"listed","path":"addro/setup/losses.py","file_url":"https://github.com/feedbackward/addro/blob/HEAD/addro/setup/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f9e3f7cfa214e9f"}},{"code_sha256_prefix":"91898e953f3b8aa0","entry":"SAM","repo":"zhuohuangai/sharpdro","repo_kind":"official","path":"sam.py","file_url":"https://github.com/zhuohuangai/sharpdro/blob/HEAD/sam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91898e953f3b8aa0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}